QuarkAudio Technical Report

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Chengwei, Yan, Haoyin, Xue, Shaofei, Liang, Xiaotao, Chen, Xiaofu, Gong, Bin, Xue, Zheng, Song, Gang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917166044938240
author Liu, Chengwei
Yan, Haoyin
Xue, Shaofei
Liang, Xiaotao
Chen, Xiaofu
Gong, Bin
Xue, Zheng
Song, Gang
author_facet Liu, Chengwei
Yan, Haoyin
Xue, Shaofei
Liang, Xiaotao
Chen, Xiaofu
Gong, Bin
Xue, Zheng
Song, Gang
contents Many existing audio processing and generation models rely on task-specific architectures, resulting in fragmented development efforts and limited extensibility. It is therefore promising to design a unified framework capable of handling multiple tasks, while providing robust instruction and audio understanding and high-quality audio generation. This requires a compatible paradigm design, a powerful backbone, and a high-fidelity audio reconstruction module. To meet these requirements, this technical report introduces QuarkAudio, a decoder-only autoregressive (AR) LM-based generative framework that unifies multiple tasks. The framework includes a unified discrete audio tokenizer, H-Codec, which incorporates self-supervised learning (SSL) representations into the tokenization and reconstruction process. We further propose several improvements to H-Codec, such as a dynamic frame-rate mechanism and extending the audio sampling rate to 48 kHz. QuarkAudio unifies tasks by using task-specific conditional information as the conditioning sequence of the decoder-only LM, and predicting discrete target audio tokens in an AR manner. The framework supports a wide range of audio processing and generation tasks, including speech restoration (SR), target speaker extraction (TSE), speech separation (SS), voice conversion (VC), and language-queried audio source separation (LASS). In addition, we extend downstream tasks to universal free-form audio editing guided by natural language instructions (including speech semantic editing and audio event editing). Experimental results show that H-Codec achieves high-quality audio reconstruction with a low frame rate, improving both the efficiency and performance of downstream audio generation, and that QuarkAudio delivers competitive or comparable performance to state-of-the-art task-specific or multi-task systems across multiple tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20151
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QuarkAudio Technical Report
Liu, Chengwei
Yan, Haoyin
Xue, Shaofei
Liang, Xiaotao
Chen, Xiaofu
Gong, Bin
Xue, Zheng
Song, Gang
Audio and Speech Processing
Sound
Many existing audio processing and generation models rely on task-specific architectures, resulting in fragmented development efforts and limited extensibility. It is therefore promising to design a unified framework capable of handling multiple tasks, while providing robust instruction and audio understanding and high-quality audio generation. This requires a compatible paradigm design, a powerful backbone, and a high-fidelity audio reconstruction module. To meet these requirements, this technical report introduces QuarkAudio, a decoder-only autoregressive (AR) LM-based generative framework that unifies multiple tasks. The framework includes a unified discrete audio tokenizer, H-Codec, which incorporates self-supervised learning (SSL) representations into the tokenization and reconstruction process. We further propose several improvements to H-Codec, such as a dynamic frame-rate mechanism and extending the audio sampling rate to 48 kHz. QuarkAudio unifies tasks by using task-specific conditional information as the conditioning sequence of the decoder-only LM, and predicting discrete target audio tokens in an AR manner. The framework supports a wide range of audio processing and generation tasks, including speech restoration (SR), target speaker extraction (TSE), speech separation (SS), voice conversion (VC), and language-queried audio source separation (LASS). In addition, we extend downstream tasks to universal free-form audio editing guided by natural language instructions (including speech semantic editing and audio event editing). Experimental results show that H-Codec achieves high-quality audio reconstruction with a low frame rate, improving both the efficiency and performance of downstream audio generation, and that QuarkAudio delivers competitive or comparable performance to state-of-the-art task-specific or multi-task systems across multiple tasks.
title QuarkAudio Technical Report
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2512.20151